Pet adoption listing clip: MiniMax H3 at 768p for 6 seconds
A shelter dog photo becomes a 6-second clip with minimax-h3 on Sume for 45 cents at 768p; stereo audio is always on, so there is no mute switch.

A shelter can turn a dog's photo into a 6-second clip with minimax-h3 at 768p for $0.45 on Sume, or $0.38 at 480p. MiniMax H3 runs 5 to 15 seconds at native 480p and 768p, and always renders stereo audio: there is no generate_audio field, so if the listing needs silence, remove the sound track after download (Video Router, read 2026-10-05).
What do I send?
Use the adoption photo as the first frame and ask for calm, natural motion. Ask only for what you can show honestly: the clip must not change the animal's markings or look.
curl -X POST https://api.sume.com/v1/videos \
-H "Authorization: Bearer $SUME_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"minimax-h3","prompt":"The dog tilts its head and wags its tail slowly, soft daylight, shallow focus","duration":6,"resolution":"768p","aspect_ratio":"9:16","frame_images":[{"type":"image_url","image_url":{"url":"https://example.com/dog.jpg"},"frame_type":"first_frame"}]}'What does a litter of listings cost?
The price depends only on seconds and resolution, so ten listings at 6 seconds cost ten times one.
| Resolution | Per second | 6-second clip | 10 clips |
|---|---|---|---|
| 480p | $0.0625 | $0.38 | $3.75 |
| 768p | $0.075 | $0.45 | $4.50 |
How do I poll and download the result?
A submit returns 202 with id, polling_url, status and model. Poll GET /v1/videos/{id} until status is completed (the other terminal values are failed and cancelled), then download from GET /v1/videos/{id}/content?index=0 with the same bearer key. H3 can also produce 2K and 4K upscales, which Sume bills only if your request includes them.
curl https://api.sume.com/v1/videos/JOB_ID -H "Authorization: Bearer $SUME_API_KEY"
curl -L "https://api.sume.com/v1/videos/JOB_ID/content?index=0" \
-H "Authorization: Bearer $SUME_API_KEY" --output clip.mp4How do I silence the stereo track?
Detach or replace the sound with the audio detach tool, or lay a music bed under the clip on a timeline.
Sources
Related posts
More in Use cases
- Pet product demo clip on Seedance 2.5: treat, toy and leash prompts
Three prompts for pet product demo clips on Seedance 2.5, one each for a treat, a toy and a leash, with 10 to 15 second prices at 480p, 720p and 1080p on Sume.
- Photographer portfolio reel: four portraits, four Seedance Fast clips
Four portraits, four 4-second 720p clips with seedance-2-fast on Sume cost $4.84; join them on a timeline for one reel.
- How Pinterest applies the AI label to a generated image Pin
Pinterest labels an image Pin when the owner says it is AI-made or its detection systems think so. Appeal steps are in a separate Help Center article.
- Pinterest carousel ad specs: 1:1 or 2:3, 2 to 5 images, 20 MB
Pinterest carousel ads take 1:1 or 2:3 images, 2 to 5 cards, 20 MB each. Render a matching set in one Sume Image API call with n and one aspect_ratio.
Written by Sume